Incorporating social impact on new product adoption in choice modeling: A case study in green vehicles

While discrete choice analysis is prevalent in capturing consumer preferences and describing their choice behaviors in product design, the traditional choice modeling approach assumes that each individual makes independent decisions, without considering the social impact. However, empirical studies show that choice is social – influenced by many factors beyond engineering performance of a product and consumer attributes. To alleviate this limitation, we propose a new choice modeling framework to capture the dynamic influence from social networks on consumer adoption of new products. By introducing social influence attributes into a choice utility function, social network simulation is integrated with the traditional discrete choice analysis in a three-stage process. Our study shows the need for considering social impact in forecasting new product adoption. Using hybrid electric vehicles as an example, our work illustrates the procedure of social network construction, social influence evaluation, and choice model estimation based on data from the National Household Travel Survey. Our study also demonstrates several interesting findings on the dynamic nature of new technology adoption and how social networks may influence hybrid electric vehicle adoption. Introduction While the use of Discrete Choice Analysis (DCA) is prevalent in modeling consumer preferences and describing their choice behaviors in product design (Frischknecht et al., individuals' choices are studied without social contexts in most cases. Empirical studies show that social context, such as ''neighbor'' effects may impact consumer choice behavior (Case, 1992). Often times, social context influences consumer attitudes towards new products, such as those involving green technology. As an example, a consumer's decision in choosing an eco-friendly alternative fuel vehicle, such as a hybrid electric vehicle (HEV) or plug-in hybrid electric vehicle (PHEV), may be influenced by neighbors and friends or others who share similar social status or profile. In the broad market of consumer products, a large amount of product reviews and recommendations are now made available through rapidly growing online shopping websites and social networking sites which accelerate the social impact on product adoption. Integrating social network simulation into consumer choice modeling and developing methods for